Abstract
TTS (Text to Speech), also known as speech synthesis, is a kind of import technology of artificial intelligence. TTS mainly includes rule-driven and data-driven two kinds of approaches. Some important approaches of TTS are articulatory synthesis, formant synthesis, concatenate synthesis, unit selection synthesis, HMM synthesis and DNN synthesis. This paper will give a simple introduction to all the approaches. Finally, these approaches are compared and the technical trend of TTS is discussed briefly.
Cite
CITATION STYLE
YIN, Z. (2017). A Simplified Overview of TTS Techniques. DEStech Transactions on Computer Science and Engineering, (aiea). https://doi.org/10.12783/dtcse/aiea2017/14929
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.